New graph-neural-network flavor tagger for Belle II and measurement of $\sin2\phi_1$ in $B^0 \to J/\psi K^0_\text{S}$ decays

Abstract

We present GFlaT, a new algorithm that uses a graph-neural-network to determine the flavor of neutral $B$ mesons produced in $\Upsilon(4S)$ decays. It improves previous algorithms by using the information from all charged final-state particles and the relations between them. We evaluate its performance using $B$ decays to flavor-specific hadronic final states reconstructed in a 362 $\text{fb}^{-1}$ sample of electron-positron collisions collected at the $\Upsilon(4S)$ resonance with the Belle II detector at the SuperKEKB collider. We achieve an effective tagging efficiency of $(37.40 \pm 0.43 \pm 0.36) \%$, where the first uncertainty is statistical and the second systematic, which is $18\%$ better than the previous Belle II algorithm. Demonstrating the algorithm, we use $B^{0}\to J/\psi K^0_\text{S}$ decays to measure the mixing-induced and direct $CP$ violation parameters, $S = (0.724 \pm 0.035 \pm 0.009)$ and $C = (-0.035 \pm 0.026 \pm 0.029)$.